Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382562102> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4382562102 abstract "The predictive performance of a neural network depends on its weights and architecture. optimizers based on gradient descent are most commonly used to optimize the weights, and grid search is utilized to find the most suitable architecture from the list of predefined architectures. On the other hand, neuroevolution offers a solution for the simultaneous growth of neural network architecture and the evolution of its weights. Thus, it is not limited by the user-defined list of possible architectures and can find configurations optimal for a specific task. Both approaches can be effectively parallelized and take advantage of modern multi-process systems. In this research, we compare neuroevolution and backpropagation in terms of the time consumed by the algorithm, the predictive performance of the neural network, and the complexity of the neural network. The total time for each algorithm is measured along with the times for each section of the algorithm and the time spent on synchronization due to the multi-process setting. The neural networks are compared by their predictive performance in terms of Matthews correlation coefficient score and their complexity as the number of nodes and connections. The case study is based on two synthetic and two real-world datasets for classification tasks." @default.
- W4382562102 created "2023-06-30" @default.
- W4382562102 creator A5014073915 @default.
- W4382562102 creator A5040101364 @default.
- W4382562102 creator A5088320075 @default.
- W4382562102 creator A5090050853 @default.
- W4382562102 date "2023-05-22" @default.
- W4382562102 modified "2023-09-28" @default.
- W4382562102 title "Neuroevolution for the Sustainable Evolution of Neural Networks" @default.
- W4382562102 cites W1547737196 @default.
- W4382562102 cites W2059185913 @default.
- W4382562102 cites W2111935653 @default.
- W4382562102 cites W2483031229 @default.
- W4382562102 cites W3045004532 @default.
- W4382562102 cites W3111221273 @default.
- W4382562102 doi "https://doi.org/10.23919/mipro57284.2023.10159943" @default.
- W4382562102 hasPublicationYear "2023" @default.
- W4382562102 type Work @default.
- W4382562102 citedByCount "0" @default.
- W4382562102 crossrefType "proceedings-article" @default.
- W4382562102 hasAuthorship W4382562102A5014073915 @default.
- W4382562102 hasAuthorship W4382562102A5040101364 @default.
- W4382562102 hasAuthorship W4382562102A5088320075 @default.
- W4382562102 hasAuthorship W4382562102A5090050853 @default.
- W4382562102 hasConcept C111919701 @default.
- W4382562102 hasConcept C118070581 @default.
- W4382562102 hasConcept C119857082 @default.
- W4382562102 hasConcept C127162648 @default.
- W4382562102 hasConcept C153258448 @default.
- W4382562102 hasConcept C154945302 @default.
- W4382562102 hasConcept C155032097 @default.
- W4382562102 hasConcept C162324750 @default.
- W4382562102 hasConcept C187736073 @default.
- W4382562102 hasConcept C2778562939 @default.
- W4382562102 hasConcept C2780451532 @default.
- W4382562102 hasConcept C31258907 @default.
- W4382562102 hasConcept C41008148 @default.
- W4382562102 hasConcept C50644808 @default.
- W4382562102 hasConcept C98045186 @default.
- W4382562102 hasConceptScore W4382562102C111919701 @default.
- W4382562102 hasConceptScore W4382562102C118070581 @default.
- W4382562102 hasConceptScore W4382562102C119857082 @default.
- W4382562102 hasConceptScore W4382562102C127162648 @default.
- W4382562102 hasConceptScore W4382562102C153258448 @default.
- W4382562102 hasConceptScore W4382562102C154945302 @default.
- W4382562102 hasConceptScore W4382562102C155032097 @default.
- W4382562102 hasConceptScore W4382562102C162324750 @default.
- W4382562102 hasConceptScore W4382562102C187736073 @default.
- W4382562102 hasConceptScore W4382562102C2778562939 @default.
- W4382562102 hasConceptScore W4382562102C2780451532 @default.
- W4382562102 hasConceptScore W4382562102C31258907 @default.
- W4382562102 hasConceptScore W4382562102C41008148 @default.
- W4382562102 hasConceptScore W4382562102C50644808 @default.
- W4382562102 hasConceptScore W4382562102C98045186 @default.
- W4382562102 hasFunder F4320335551 @default.
- W4382562102 hasLocation W43825621021 @default.
- W4382562102 hasOpenAccess W4382562102 @default.
- W4382562102 hasPrimaryLocation W43825621021 @default.
- W4382562102 hasRelatedWork W1183256782 @default.
- W4382562102 hasRelatedWork W1489050811 @default.
- W4382562102 hasRelatedWork W2018863220 @default.
- W4382562102 hasRelatedWork W2146640810 @default.
- W4382562102 hasRelatedWork W2435007635 @default.
- W4382562102 hasRelatedWork W3123071383 @default.
- W4382562102 hasRelatedWork W3159389381 @default.
- W4382562102 hasRelatedWork W3170244987 @default.
- W4382562102 hasRelatedWork W3185486575 @default.
- W4382562102 hasRelatedWork W1629725936 @default.
- W4382562102 isParatext "false" @default.
- W4382562102 isRetracted "false" @default.
- W4382562102 workType "article" @default.